Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5949 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.9399. Min Act: -0.1700
Data Index: 3675060 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.8774. Min Act: -0.1700
Data Index: 8696675 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.8774. Min Act: -0.1700
Data Index: 2600103 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.8461. Min Act: -0.1700
Data Index: 5241126 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.8461. Min Act: -0.1700
Data Index: 8293225 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.8461. Min Act: -0.1700
Data Index: 5309326 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.8461. Min Act: -0.1700
Data Index: 2531698 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.8148. Min Act: -0.1700
Data Index: 5157764 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.8148. Min Act: -0.1700
Data Index: 4991287 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.8148. Min Act: -0.1700
Data Index: 6443462 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.8148. Min Act: -0.1700
Data Index: 2323766 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.7836. Min Act: -0.1700
Data Index: 7158391 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.7836. Min Act: -0.1700
Data Index: 8021676 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.7836. Min Act: -0.1700
Data Index: 131912 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.7836. Min Act: -0.1700
Data Index: 6156030 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.7836. Min Act: -0.1700
Data Index: 4785211 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.7836. Min Act: -0.1700
Data Index: 5667225 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.7836. Min Act: -0.1700
Data Index: 5654156 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.7836. Min Act: -0.1700
Data Index: 3718588 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9399. Min Range: -3.9399
Max Act: 3.7523. Min Act: -0.1700
Data Index: 5251748 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19